半導體封裝測試業所使用的機台動作相當繁複，使得機台測試屬性的設定方法較難以物理公式去做推演。本研究的目的是使用類神經網路模式化機台複雜的行為以及對應機台的設定，並找出實際重要測試程式屬性的方式。
將機台屬性以類神經網路加以訓練，使用給定的機台屬性去幫助機台做設定，並推廣到其它機台中，選出與我們期望的設備表現及機台規格結果最相近的機台(Tool Matching)；另一方面，測試機在整個封裝測試廠中屬於相對昂貴的機台，測試程式的技術面主要來自於客戶端，國內並沒有自行撰寫的技術方式，然而藉由大量執行測試以及修改的經驗值，本文研究希望能將這些龐大的經驗值轉化為自身的價值，進而衍發出自行撰寫測試程式的能力。測試程式動輒上千道程序，如何在學得撰寫測試程式的過程中進而去蕪存菁只留下必要且具絕對性的測試屬性尤其重要。本研究利用導傳遞類神經網路 ( Back-Propagation Network ) 幫助找出最重要機台設定屬性進而達到節省測試時間的目的。
關鍵字：類神經網路、倒傳遞類神經網路、IC測試

In the semiconductor assembly and test (A/T) industry, using physics equations to deduce the parameter settings of machines is difficult due to complicated machine movements. Therefore, the purpose of this research is to use neural network to modelize the complex machine behaviors and tool parameter settings and then determine the practical key parameters for test programs.

After modelizing the machine attributes with neural network, these attributes were trained and then applied to assist machine settings by using the given machine attributes. The same procedures were implemented in several machines and afterwards the tool matching machine with the performance that is nearest to the expected result and specification was selected to collect the production data. In all A/T factories, test machines are relatively expensive and the test programs are mainly owned by customers; therefore, the techniques of writing test programs are barely existed domestically. However, there is an enormous amount of experience in executing tests and partial modifications. This paper aims to develop the domestic ability of writing test programs through transforming these experiences into self values. Furthermore, there are thousands of procedures in test programs, so how to refine parameters and identify the essential ones in the process of accumulating the ability of writing test programs is extraordinary important. In this study, using neural network back-propagation algorithm, the most crucial parameters were determined and the purpose of developing more efficient test processes was achieved as well.
Keywords : Neural network, Back propagation, IC test

摘要………………………………………………………………………………i
誌謝………………………………………………………………………………iii
目錄………………………………………………………………………………iv
圖目錄……………………………………………………………………………vi
表目錄……………………………………………………………………………viii
第一章 緒論………………………………………………………………………1
1.1 研究背景…………………………………………………………………1
1.2 研究目的…………………………………………………………………1
1.3 論文架構與執行步驟……………………………………………………2
第二章 IC封裝測試製程概述……………………………………………………4
2.1 IC封裝種類與封裝測試流程介紹………………………………………6
第三章 類神經網路………………………………………………………………20
3.1 簡介………………………………………………………………………20
3.2 倒傳遞類神經網路………………………………………………………20
3.3 類神經網路應用…………………………………………………………25
第四章 研究方法…………………………………………………………………26
4.1 研究方法設計……………………………………………………………26
第五章 個案研究…………………………………………………………………28
5.1 個案公司簡介……………………………………………………………28
5.2 個案執行…………………………………………………………………29
5.2.1 資料前處理………………………………………………………………29
5.2.2 資料分割與類神經網路建構……………………………………………31
5.2.3 模型訓練以及準確度確認………………………………………………33
5.2.4 屬性個數決定……………………………………………………………34
第六章 結論………………………………………………………………………35
6.1 研究結論…………………………………………………………………35
6.2 主要效益…………………………………………………………………35
6.3 未來研究建議……………………………………………………………36
參考文獻……………………………………………………………………………37

1.C.T. Su, H.H. Hsu, C.H. Tsai, 2002, “Knowledge Mining From Trained Neural Networks”, Journal of Computer Information Systems, Vol.42, No.4, pp. 61–70
2.Su et al., 2006, “Data Mining for The Diagnosis of Type II Diabetes From Three-dimensional Body Surface Anthropometrical Scanning Data”, Journal of Computer & Mathematics with Applications, Vol.51, No. 6–7, pp. 1075–1092
3.Moganti, M., Ercal, F. and Dagli, C. H., 1995, Printed Circuit Board Inspection: A Novel Ppproach, Proceedings of World Congress on Neural Networks, Vol.2, pp.563-566.
4.Moganti, M., Ercal, F., Dagli, C. H. and Tsunekawa, S.,1996, Automatic PCB Inspection Algorithms: A Survey, Computer Vision and Image Understanding, Vol.63, No.2, pp.287-313.
5.Chou, P. B., Ravishankar, R., Sturzenbecker, M. C.,Wu, F. Y. and Brecher, V. H.,
1997, Automatic Defect Classification for Semiconductor Manufacturing, Machine Vision and Applications, Vol.9, No.4, pp. 201-214.
6.蘇木春、張孝德1999，機器學習：類神經網路、模糊系統以及基因演算法，全華科技圖書
7.蘇朝墩2013，品質工程，前程文化
8.羅華強2005，類神經網路-MATLAB 的應用，第2版，高立圖書
9.葉怡成2007，類神經網路模式應用與實作，儒林圖書
10.謝邦昌2001，Data Mining 在企業上的應用，統計學報，第24期，pp.34-39